Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

He felt his face flush as he walked into the shop, a place he usually avoided. Seeing the ring, the one he knew so well, encased in glass, provoked a wave of nausea. The ring’s beauty, the way it caught the light, felt diminished now, tarnished by its surroundings.

The owner, a woman with a sharp gaze, watched him with a curious expression. She tapped her pen on the counter, waiting. He swallowed, the words catching in his throat.

"That... that's my grandmother's ring," he finally managed, his voice strained. The woman raised an eyebrow, her expression unchanged. The fact that she didn’t immediately recognize the ring, that she saw it as just another piece of jewelry, scraped against his sensibilities.

Emotion: insulted

Cluster: Anger / Hostility
PC1 (Valence): -0.98 Negative
PC2 (Disposition): 1.46

Role in Research

This story is one of 1,000 stories generated for the emotion insulted. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 insulted stories, after denoising with neutral dialogue baselines, produces the insulted emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the insulted vector is projected through the unembedding matrix.

Promoted:
l0.354
骂0.277
愤0.267
C0.237
🤬0.233
Suppressed:
own-0.325
давно-0.229
adventurous-0.223
soon-0.219
optimistic-0.217